Python cluster.normalized_mutual_info_score方法代码示例

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test_perfect_matches():
    for score_func in score_funcs:
        assert_equal(score_func([], []), 1.0)
        assert_equal(score_func([0], [1]), 1.0)
        assert_equal(score_func([0, 0, 0], [0, 0, 0]), 1.0)
        assert_equal(score_func([0, 1, 0], [42, 7, 42]), 1.0)
        assert_equal(score_func([0., 1., 0.], [42., 7., 42.]), 1.0)
        assert_equal(score_func([0., 1., 2.], [42., 7., 2.]), 1.0)
        assert_equal(score_func([0, 1, 2], [42, 7, 2]), 1.0)
    score_funcs_with_changing_means = [
        normalized_mutual_info_score,
        adjusted_mutual_info_score,
    ]
    means = {"min", "geometric", "arithmetic", "max"}
    for score_func in score_funcs_with_changing_means:
        for mean in means:
            assert score_func([], [], mean) == 1.0
            assert score_func([0], [1], mean) == 1.0
            assert score_func([0, 0, 0], [0, 0, 0], mean) == 1.0
            assert score_func([0, 1, 0], [42, 7, 42], mean) == 1.0
            assert score_func([0., 1., 0.], [42., 7., 42.], mean) == 1.0
            assert score_func([0., 1., 2.], [42., 7., 2.], mean) == 1.0
            assert score_func([0, 1, 2], [42, 7, 2], mean) == 1.0 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def init_prob_kmeans(model, eval_loader, args):
    torch.manual_seed(1)
    model = model.to(device)
    # cluster parameter initiate
    model.eval()
    targets = np.zeros(len(eval_loader.dataset)) 
    feats = np.zeros((len(eval_loader.dataset), 512))
    for _, (x, label, idx) in enumerate(eval_loader):
        x = x.to(device)
        feat = model(x)
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.data.cpu().numpy()
        targets[idx] = label.data.cpu().numpy()
    pca = PCA(n_components=args.n_clusters)
    feats = pca.fit_transform(feats)
    kmeans = KMeans(n_clusters=args.n_clusters, n_init=20)
    y_pred = kmeans.fit_predict(feats) 
    acc, nmi, ari = cluster_acc(targets, y_pred), nmi_score(targets, y_pred), ari_score(targets, y_pred)
    print('Init acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = feat2prob(torch.from_numpy(feats), torch.from_numpy(kmeans.cluster_centers_))
    return acc, nmi, ari, kmeans.cluster_centers_, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test(model, test_loader, args):
    model.eval()
    acc_record = AverageMeter()
    preds=np.array([])
    targets=np.array([])
    feats = np.zeros((len(test_loader.dataset), args.n_clusters))
    probs= np.zeros((len(test_loader.dataset), args.n_clusters))
    for batch_idx, (x, label, idx) in enumerate(tqdm(test_loader)):
        x, label = x.to(device), label.to(device)
        feat = model(x)
        prob = feat2prob(feat, model.center)
        _, pred = prob.max(1)
        targets=np.append(targets, label.cpu().numpy())
        preds=np.append(preds, pred.cpu().numpy())
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.cpu().detach().numpy()
        probs[idx, :] = prob.cpu().detach().numpy()
    acc, nmi, ari = cluster_acc(targets.astype(int), preds.astype(int)), nmi_score(targets, preds), ari_score(targets, preds)
    print('Test acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = torch.from_numpy(probs)
    return acc, nmi, ari, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def init_prob_kmeans(model, eval_loader, args):
    torch.manual_seed(1)
    model = model.to(device)
    # cluster parameter initiate
    model.eval()
    targets = np.zeros(len(eval_loader.dataset)) 
    feats = np.zeros((len(eval_loader.dataset), 512))
    for _, (x, label, idx) in enumerate(eval_loader):
        x = x.to(device)
        feat = model(x)
        feat = feat.view(x.size(0), -1)
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.data.cpu().numpy()
        targets[idx] = label.data.cpu().numpy()
    # evaluate clustering performance
    pca = PCA(n_components=args.n_clusters)
    feats = pca.fit_transform(feats)
    kmeans = KMeans(n_clusters=args.n_clusters, n_init=20)
    y_pred = kmeans.fit_predict(feats) 
    acc, nmi, ari = cluster_acc(targets, y_pred), nmi_score(targets, y_pred), ari_score(targets, y_pred)
    print('Init acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = feat2prob(torch.from_numpy(feats), torch.from_numpy(kmeans.cluster_centers_))
    return acc, nmi, ari, kmeans.cluster_centers_, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test(model, test_loader, args, epoch=0):
    model.eval()
    acc_record = AverageMeter()
    preds=np.array([])
    targets=np.array([])
    feats = np.zeros((len(test_loader.dataset), args.n_clusters))
    probs = np.zeros((len(test_loader.dataset), args.n_clusters))
    for batch_idx, (x, label, idx) in enumerate(tqdm(test_loader)):
        x, label = x.to(device), label.to(device)
        output = model(x)
        prob = feat2prob(output, model.center)
        _, pred = prob.max(1)
        targets=np.append(targets, label.cpu().numpy())
        preds=np.append(preds, pred.cpu().numpy())
        idx = idx.data.cpu().numpy()
        feats[idx, :] = output.cpu().detach().numpy()
        probs[idx, :]= prob.cpu().detach().numpy()
    acc, nmi, ari = cluster_acc(targets.astype(int), preds.astype(int)), nmi_score(targets, preds), ari_score(targets, preds)
    print('Test acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    return acc, nmi, ari, torch.from_numpy(probs) 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def init_prob_kmeans(model, eval_loader, args):
    torch.manual_seed(1)
    model = model.to(device)
    # cluster parameter initiate
    model.eval()
    targets = np.zeros(len(eval_loader.dataset)) 
    feats = np.zeros((len(eval_loader.dataset), 512))
    for _, (x, label, idx) in enumerate(eval_loader):
        x = x.to(device)
        feat = model(x)
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.data.cpu().numpy()
        targets[idx] = label.data.cpu().numpy()
    # evaluate clustering performance
    pca = PCA(n_components=args.n_clusters)
    feats = pca.fit_transform(feats)
    kmeans = KMeans(n_clusters=args.n_clusters, n_init=20)
    y_pred = kmeans.fit_predict(feats) 
    acc, nmi, ari = cluster_acc(targets, y_pred), nmi_score(targets, y_pred), ari_score(targets, y_pred)
    print('Init acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = feat2prob(torch.from_numpy(feats), torch.from_numpy(kmeans.cluster_centers_))
    return acc, nmi, ari, kmeans.cluster_centers_, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test(model, test_loader, args):
    model.eval()
    preds=np.array([])
    targets=np.array([])
    feats = np.zeros((len(test_loader.dataset), args.n_clusters))
    probs= np.zeros((len(test_loader.dataset), args.n_clusters))
    for batch_idx, (x, label, idx) in enumerate(tqdm(test_loader)):
        x, label = x.to(device), label.to(device)
        feat = model(x)
        prob = feat2prob(feat, model.center)
        _, pred = prob.max(1)
        targets=np.append(targets, label.cpu().numpy())
        preds=np.append(preds, pred.cpu().numpy())
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.cpu().detach().numpy()
        probs[idx, :] = prob.cpu().detach().numpy()
    acc, nmi, ari = cluster_acc(targets.astype(int), preds.astype(int)), nmi_score(targets, preds), ari_score(targets, preds)
    print('Test acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = torch.from_numpy(probs)
    return acc, nmi, ari, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test(model, test_loader, args, epoch='test'):
    model.eval()
    preds=np.array([])
    targets=np.array([])
    feats = np.zeros((len(test_loader.dataset), args.n_clusters))
    probs= np.zeros((len(test_loader.dataset), args.n_clusters))
    for batch_idx, (x, label, idx) in enumerate(tqdm(test_loader)):
        x, label = x.to(device), label.to(device)
        _, feat = model(x)
        prob = feat2prob(feat, model.center)
        _, pred = prob.max(1)
        targets=np.append(targets, label.cpu().numpy())
        preds=np.append(preds, pred.cpu().numpy())
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.cpu().detach().numpy()
        probs[idx, :] = prob.cpu().detach().numpy()
    acc, nmi, ari = cluster_acc(targets.astype(int), preds.astype(int)), nmi_score(targets, preds), ari_score(targets, preds)
    print('Test acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = torch.from_numpy(probs)
    return acc, nmi, ari, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def init_prob_kmeans(model, eval_loader, args):
    torch.manual_seed(1)
    model = model.to(device)
    # cluster parameter initiate
    model.eval()
    targets = np.zeros(len(eval_loader.dataset)) 
    feats = np.zeros((len(eval_loader.dataset), 1024))
    for _, (x, _, label, idx) in enumerate(eval_loader):
        x = x.to(device)
        _, feat = model(x)
        feat = feat.view(x.size(0), -1)
        idx = idx.data.cpu().numpy()
        feats[idx, :] = feat.data.cpu().numpy()
        targets[idx] = label.data.cpu().numpy()
    # evaluate clustering performance
    pca = PCA(n_components=args.n_clusters)
    feats = pca.fit_transform(feats)
    kmeans = KMeans(n_clusters=args.n_clusters, n_init=20)
    y_pred = kmeans.fit_predict(feats) 
    acc, nmi, ari = cluster_acc(targets, y_pred), nmi_score(targets, y_pred), ari_score(targets, y_pred)
    print('Init acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = feat2prob(torch.from_numpy(feats), torch.from_numpy(kmeans.cluster_centers_))
    return kmeans.cluster_centers_, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test(model, eval_loader, args):
    model.eval()
    targets = np.zeros(len(eval_loader.dataset)) 
    y_pred = np.zeros(len(eval_loader.dataset)) 
    probs= np.zeros((len(eval_loader.dataset), args.n_clusters))
    for _, (x, _, label, idx) in enumerate(eval_loader):
        x = x.to(device)
        _, feat = model(x)
        prob = feat2prob(feat, model.center)
        #  prob = F.softmax(logit, dim=1)
        idx = idx.data.cpu().numpy()
        y_pred[idx] = prob.data.cpu().detach().numpy().argmax(1)
        targets[idx] = label.data.cpu().numpy()
        probs[idx, :] = prob.cpu().detach().numpy()
    # evaluate clustering performance
    y_pred = y_pred.astype(np.int64)
    acc, nmi, ari = cluster_acc(targets, y_pred), nmi_score(targets, y_pred), ari_score(targets, y_pred)
    print('Test acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = torch.from_numpy(probs)
    return acc, nmi, ari, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test(model, eval_loader, args):
    model.eval()
    targets = np.zeros(len(eval_loader.dataset)) 
    y_pred = np.zeros(len(eval_loader.dataset)) 
    probs= np.zeros((len(eval_loader.dataset), args.n_clusters))
    for _, (x, _, label, idx) in enumerate(eval_loader):
        x = x.to(device)
        _, feat = model(x)
        prob = feat2prob(feat, model.center)
        idx = idx.data.cpu().numpy()
        y_pred[idx] = prob.data.cpu().detach().numpy().argmax(1)
        targets[idx] = label.data.cpu().numpy()
        probs[idx, :] = prob.cpu().detach().numpy()
    # evaluate clustering performance
    y_pred = y_pred.astype(np.int64)
    acc, nmi, ari = cluster_acc(targets, y_pred), nmi_score(targets, y_pred), ari_score(targets, y_pred)
    print('Test acc {:.4f}, nmi {:.4f}, ari {:.4f}'.format(acc, nmi, ari))
    probs = torch.from_numpy(probs)
    return acc, nmi, ari, probs 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test_nmi_faiss(embeddings, labels):
    res = faiss.StandardGpuResources()
    flat_config = faiss.GpuIndexFlatConfig()
    flat_config.device = 0

    unique_labels = np.unique(labels)
    d = embeddings.shape[1]
    kmeans = faiss.Clustering(d, unique_labels.size)
    kmeans.verbose = True
    kmeans.niter = 300
    kmeans.nredo = 10
    kmeans.seed = 0

    index = faiss.GpuIndexFlatL2(res, d, flat_config)

    kmeans.train(embeddings, index)

    dists, pred_labels = index.search(embeddings, 1)

    pred_labels = pred_labels.squeeze()

    nmi = normalized_mutual_info_score(labels, pred_labels)

    print("NMI: {}".format(nmi))
    return nmi 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def evaluation(X, Y, Kset):
    num = X.shape[0]
    classN = np.max(Y)+1
    kmax = np.max(Kset)
    recallK = np.zeros(len(Kset))
    #compute NMI
    kmeans = KMeans(n_clusters=classN).fit(X)
    nmi = normalized_mutual_info_score(Y, kmeans.labels_, average_method='arithmetic')
    #compute Recall@K
    sim = X.dot(X.T)
    minval = np.min(sim) - 1.
    sim -= np.diag(np.diag(sim))
    sim += np.diag(np.ones(num) * minval)
    indices = np.argsort(-sim, axis=1)[:, : kmax]
    YNN = Y[indices]
    for i in range(0, len(Kset)):
        pos = 0.
        for j in range(0, num):
            if Y[j] in YNN[j, :Kset[i]]:
                pos += 1.
        recallK[i] = pos/num
    return nmi, recallK 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test_future_warning():
    score_funcs_with_changing_means = [
        normalized_mutual_info_score,
        adjusted_mutual_info_score,
    ]
    warning_msg = "The behavior of "
    args = [0, 0, 0], [0, 0, 0]
    for score_func in score_funcs_with_changing_means:
        assert_warns_message(FutureWarning, warning_msg, score_func, *args) 

# 需要导入模块: from sklearn.metrics import cluster [as 别名]
# 或者: from sklearn.metrics.cluster import normalized_mutual_info_score [as 别名]
def test_exactly_zero_info_score():
    # Check numerical stability when information is exactly zero
    for i in np.logspace(1, 4, 4).astype(np.int):
        labels_a, labels_b = (np.ones(i, dtype=np.int),
                              np.arange(i, dtype=np.int))
        assert_equal(normalized_mutual_info_score(labels_a, labels_b), 0.0)
        assert_equal(v_measure_score(labels_a, labels_b), 0.0)
        assert_equal(adjusted_mutual_info_score(labels_a, labels_b), 0.0)
        assert_equal(normalized_mutual_info_score(labels_a, labels_b), 0.0)
        for method in ["min", "geometric", "arithmetic", "max"]:
            assert adjusted_mutual_info_score(labels_a, labels_b,
                                              method) == 0.0
            assert normalized_mutual_info_score(labels_a, labels_b,
                                                method) == 0.0